Research map / Probabilistic and scientific modeling / Dynamical systems
Disentangled behavioural representations
Amir Dezfouli, Hassan Ashtiani, Omar Ghattas, Richard Nock, Peter Dayan, Cheng Soon Ong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add separation loss L_SEP to the training objective (ablation) | Behavioral autoencoder with hypernetwork RNN decoder · Synthetic Q-learning agents | separation of latent dimensions' effects on behavior | Improved |
| use RNN learning network instead of fixed Q-learning model | Behavioral autoencoder · BD dataset (bipolar, depression, healthy) | capturing switching after reward | Improved |
| per-sequence latent representations instead of one RNN per diagnostic group | Behavioral autoencoder · BD dataset | individual-difference extraction | Improved |
| combine MMD and KL terms in the disentanglement loss (ablation) | Behavioral autoencoder · Synthetic data | latent quality | Improved |
Closest papers by meaning
- Exploring Behavior-Relevant and Disentangled Neural Dynamics with Generative Diffusion Models (NeurIPS 2024 · similarity 0.88)
- Cognitive Model Discovery via Disentangled RNNs (NeurIPS 2023 · similarity 0.87)
- Representation Learning for Integrating Multi-domain Outcomes to Optimize Individualized Treatment (NeurIPS 2020 · similarity 0.87)
- Disentangling Representations through Multi-task Learning (ICLR 2025 · similarity 0.87)
- Integrated accounts of behavioral and neuroimaging data using flexible recurrent neural network models (NeurIPS 2018 · similarity 0.86)
- Disentangled Representation Learning in Non-Markovian Causal Systems (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
